Skip to main content
Glama
Sign In

Microsoft Ads MCP by InsightfulPipe

by com.insightfulpipe
OverviewDiscussionsAdmin

Server Details

Hosted Microsoft Ads MCP server, with each action switched on or off per account.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
Insightful-Pipe/microsoft-ads-mcp-server
GitHub Stars
0
Server Listing
Microsoft Ads MCP Server
ChatGPT
–
Claude
–

TDQS

A3.7/5.0

Scored across 4 tools

Disambiguation2/5

execute_action and query_data are both labeled as the final workflow step and require the same prerequisite calls, making their read/write or action/query boundary unclear. query_contexts and query_data also overlap because both deal with planning and executing Microsoft Ads requests, so an agent could easily misselect between them.

Naming Consistency3/5

Three tools use a verb_noun pattern (execute_action, query_contexts, query_data), but prompts_menu is noun_noun and breaks the pattern. The names remain readable, but the set is not fully consistent.

Tool Count4/5

Four tools is within a reasonable range for a workflow-oriented server and avoids tool bloat. However, the set includes two very similar final-step tools plus a separate prompt catalog tool, so it is slightly less focused than ideal.

Completeness4/5

The generic execute_action and query_data tools, backed by query_contexts for discovering available actions and schemas, provide broad coverage of Microsoft Ads operations. There are minor gaps in explicit lifecycle clarity and the prompts_menu tool feels auxiliary rather than core, but agents can still reach the necessary operations.

Available Tools

4 tools
execute_actionMicrosoft Ads Execute ActionA
Destructive
Inspect

Execute Microsoft Ads action (Step 3 (FINAL) of workflow).

REQUIRED: Complete these steps first using query_contexts:

  1. request='accounts' - Get workspace_id, brand_id, ad_account_id AND available_actions

  2. request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] - Get detailed body structure for specific action(s) using actions from available_actions

IMPORTANT: Always call step 2 to see the exact body structure before executing.

Rely on info from steps 1-2 to construct the action body. Follow the schema exactly.

Inputs: body (required). Returns: object

prompts_menuMicrosoft Ads PromptsA
Read-only
Inspect

Browse the Microsoft Ads prompt catalog.

  1. request='menu' – List public/system prompts (optionally pass workspace_id + prompt_type).

  2. request='prompt_details' – Fetch prompt body by prompt_id. Set is_custom=True + workspace_id for workspace prompts.

Inputs: request (required), is_custom, prompt_id, prompt_type, +1 more. Returns: object

query_contextsMicrosoft Ads Setup HelperA
Read-only
Inspect

Helper for planning InsightfulPipe Microsoft Ads data queries.

Step 1: request='accounts' – Retrieve workspace_id, brand_id, ad_account_id, other source metadata, AND available_actions (all tables you can query).

Step 2: request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] – REQUIRED before querying. Replace with actions from available_actions to get the exact request body, required identifiers, fields, time ranges, and notes for each action.

Optional: request='available_actions' – Standalone call to list all available tables/actions (already included in accounts response).

Optional: request='brands' with brand_id + workspace_id to pull brand guidelines.

Inputs: request (required), actions, brand_id, platform, +1 more. Returns: object

query_dataMicrosoft Ads Data QueryA
Read-only
Inspect

Query Microsoft Ads data (Step 3 (FINAL) of workflow).

REQUIRED: Complete these steps first using query_contexts:

  1. request='accounts' - Get workspace_id, brand_id, ad_account_id AND available_actions

  2. request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] - Get detailed body structure for specific action(s) using actions from available_actions

IMPORTANT: Always call step 2 to see the exact body structure before querying.

Rely on info from steps 1-2 to construct the query body. Follow the schema exactly.

Inputs: body (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • bing-ads-mcp

      xar
      F
      license
      Not graded
      quality
      D
      maintenance
      MCP server enabling AI assistants to manage Microsoft Advertising (Bing Ads) campaigns, including campaigns, ad groups, keywords, and ad extensions via a clean set of tools.
      -
    • Jepto MCP

      Jepto MCPofficial

      jepto
      A
      license
      Not graded
      quality
      B
      maintenance
      A hosted remote MCP server that connects marketing platforms such as Google Ads, GA4, Search Console, Meta Ads, Microsoft Ads, LinkedIn Ads, TikTok Ads, and Google Business Profile, enabling plain-English performance analysis, KPI and budget tracking, report creation, and previewed account changes.
      8
      MIT
    • Opus Growth MCP Connector

      Opus Growth MCP Connectorofficial

      opusgrowth
      A
      license
      Not graded
      quality
      B
      maintenance
      A hosted MCP server that enables managing Google Ads, Microsoft Advertising, TikTok Ads, LinkedIn Ads, and other Google services from ChatGPT, Claude, or any MCP client using natural language, with no code or API keys required.
      MIT

    • microsoft-ads-mcp

      shinypebble
      A
      license
      A
      quality
      C
      maintenance
      MCP server for Microsoft Advertising (Bing Ads) REST API enabling agent-led campaign management and reporting. It provides tools to manage campaigns, ad groups, keywords, ads, budgets, and pull performance reports.
      66
      MIT
    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources